DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition

• URL: http://arxiv.org/abs/2211.08104v1
• Date: Tue, 15 Nov 2022 12:50:59 GMT
• Title: DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition
• Authors: Jiali Zeng, Yufan Jiang, Yongjing Yin, Xu Wang, Binghuai Lin, Yunbo Cao
• Abstract summary: DualNER is a framework to make full use of both annotated source language corpus and unlabeled target language text. We combine two complementary learning paradigms of NER, i.e., sequence labeling and span prediction, into a unified multi-task framework.
• Score: 27.245171237640502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two complementary learning paradigms of NER, i.e., sequence labeling and span prediction, into a unified multi-task framework. After obtaining a sufficient NER model trained on the source data, we further train it on the target data in a {\it dual-teaching} manner, in which the pseudo-labels for one task are constructed from the prediction of the other task. Moreover, based on the span prediction, an entity-aware regularization is proposed to enhance the intrinsic cross-lingual alignment between the same entities in different languages. Experiments and analysis demonstrate the effectiveness of our DualNER. Code is available at https://github.com/lemon0830/dualNER.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.